When Large Language Models (LLMs) walk into a Bachelor’s in optometry examination: Comparing the performances of LLMs and bachelor of optometry students

Key Points

• The study aims to evaluate how well large language models perform compared to bachelor of optometry students in examinations.
• Compared performances of LLMs and bachelor of optometry students in theoretical assessments.
• Analyzed readability of Gemini and DeepSeek models.
• Evaluated clinical reasoning skills of LLMs versus students.
• LLMs matched students in theoretical performance.
• LLMs showed lower performance in clinical reasoning.
• Gemini and DeepSeek models had superior readability and potential as educational tools.